Speech communication system and method with human-machine coordination
a communication system and human-machine technology, applied in the field of intelligent communication, can solve the problems of difficult to work independently purely by the speech robot, low information transmission efficiency of the outgoing call, and inability to meet client requirements
Active Publication Date: 2022-07-05
NANJING SILICON INTELLIGENCE TECH CO LTD
View PDF23 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Benefits of technology
[0007]An objective of the present disclosure is to provide a speech communication system and method with human-machine coordination. In this way, during a call, a seamless switchover between a human agent and a speech robot is achieved, and after a manual intervention, an attendant can quickly understand a call intention, thus ensuring good call experience of a client.
[0072]In view of the above, according to the present disclosure, the human agent may be intelligently prompted by the intervention prompting module, and the attendant is prompted at most proper time to intervene in, avoiding a bad client call caused by that the speech robot cannot well reply the client and a person does not perform an intervention in time.
[0073]The present disclosure is not intended to recognize text through the conversional ASR and then recognize an intention by NLP, but to directly recognize a user intention from speech by the speech intention understanding model, being obviously superior to a conventional method in effects, efficiency, and costs.
[0074]During a call, through the manual intervention module, the call intention before an intervention is displayed by the retrieving and prompting submodule, and the attendant is not required to understand all the call content but directly learns the client intention. In this way, time for understanding is stored, and call experience of the client is not affected by a human-machine switchover. During the call process, the client intention is intelligently recognized, and the corresponding reply content is retrieved to prompt the attendant. Thus, the attendant responds a relevant question more quickly, thereby improving service efficiency and ensuring call experience of the client.
[0075]The voice that is of the attendant corresponding to the human agent and is generated by the voice cloning module makes the client feel that he or she is communicating with an attendant of the human agent all the time, achieving a seamless switchover between a person and the speech robot. In this way, better call feelings can be provided for the client.
[0076]Manners of manual intervention are not limited to replying by speech by a particular attendant, and the client may be served by multiple people and different people. In this way, better call experience can be provided for the client.
Problems solved by technology
However, by purely a speech robot, there is a problem that information transmission efficiency of an outgoing call is not high; or that the speech robot cannot handle the question if the question of the client is complex and is out of the template, so that client requirements cannot be satisfied.
Moreover, due to such a perception that the existing speech robot in the market is not intelligent enough, clients are generally averse to communicating with the speech robot.
Therefore, it is difficult to work independently purely by the speech robot.
Compared with the speech robot, a purely manual labor has advantages in accumulation of common knowledge and emotion recognition, and can flexibly handle conditions that are more complex; but has a limited workload affordable, an intense emotional fluctuation, and uneven professional levels.
For example, for telesales, a true challenge for an attendant of a human agent usually is not from professionality insufficiency, but from frustration when the client refuses and rings off.
However, after the human-machine switchover, the attendant needs some time to acquire conversation information between the speech robot and the client.
Particularly, the client needs to give time for the attendant to comb call content while facing that information is acquired from the speech robot in low efficiency, resulting in a bad client experience to the client.
Thus, the client may be caused to have a feeling of dislike or even disgust.
As a result, a problem occurs that it is difficult to reach an objective of the call.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0079]The present disclosure is described in detail below with reference to the accompanying drawings and the specific embodiments. Obviously, the described embodiments are merely some and not all of embodiments in accordance with the present disclosure. According to the embodiments of the present disclosure, all other embodiments derived by persons of ordinary skills in the art without an effective effort fall within the protection scope of the present disclosure.
[0080]As shown in FIG. 1, the present disclosure provides a speech communication system with human-machine coordination, including a communications module; an answering and calling-out module, allocating a human agent after a call is connected;
[0081]a speech intention understanding module including a speech intention understanding model, for understanding an intention in a call process;
[0082]a voice cloning module including a voice cloning model, for synthesizing a reply text into voice of a corresponding attendant;
[0083]a...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present disclosure relates to a field of intelligent communications, and discloses a speech communication system and method with human-machine coordination, which resolve a problem of bad client experience because great differences occur after a switchover in a call through a prior human-machine coordination and time of a client is wasted. Key points of the technical solutions of the present disclosure include a communications module; an answering and calling-out module, allocating a human agent; a speech intention understanding module for understanding an intention in a call process; a voice cloning module, synthesizing, from a reply text, voice of a corresponding attendant; a human-machine interaction module, to communicate with a client by a speech robot; an intervention prompting module, monitoring call content to obtain an intervention willing probability, and prompting the human agent according to a predefined rule; and a manual intervention module, through which the client is replied by a person, and the manual intervention module displays a call intention and prompts the call during the call. In this way, during the call, a seamless switchover may be performed between the human agent and the speech robot. After the manual intervention, the attendant can quickly understand the call intention, to ensure good call experience of the client.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application is a U.S. National Phase Application under 35 U.S.C. 371 of International Application No. PCT / CN2021 / 085323, filed on Apr. 2, 2021, which claims priority to the Chinese Application No. 202010346872.9, filed with the China National Intellectual Property Administration on Apr. 28, 2020 and entitled “SPEECH COMMUNICATION SYSTEM AND METHOD WITH HUMAN-MACHINE COORDINATION”, the entire disclosures of the above applications are expressly incorporated by reference herein.FIELD OF THE INVENTION[0002]The present disclosure relates to the field of intelligent communications, and in particular, to a speech communication system and method with human-machine coordination.BACKGROUND OF THE INVENTION[0003]With rapid development of AI and a communication technology, speech robots have been widely applied to various industries. For example, when there is a need for an enterprise to communicate with potential clients, the speech robot can s...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityPatents(United States)
IPC IPC(8): G10L15/22G10L13/033G10L15/26G10L19/032H04M3/51
CPCG10L15/22G10L13/033G10L15/26G10L19/032H04M3/5166G10L15/063G10L13/00H04M3/527H04M2201/40H04M2201/39
InventorSIMA, HUAPENG
OwnerNANJING SILICON INTELLIGENCE TECH CO LTD